---
title: "Coronavirus"
output: 
  flexdashboard::flex_dashboard:
    orientation: rows
    social: menu
    source_code: embed
    vertical_layout: fill
---

```{r setup, include=FALSE}
#------------------ Packages ------------------
library(flexdashboard)
library(leaflet)
library(leafpop)
library(purrr)

library(coronavirus)
library(covid19italy)

data(coronavirus)
data(italy_total)

`%>%` <- magrittr::`%>%`
#------------------ Parameters ------------------
# Set colors
# https://www.w3.org/TR/css-color-3/#svg-color
confirmed_color <- "purple"
active_color <- "#1f77b4"
recovered_color <- "forestgreen"
death_color <- "red"
#------------------ Data ------------------
df <- coronavirus %>% 
  # dplyr::filter(date == max(date)) %>%
  dplyr::group_by(Country.Region, type) %>%
  dplyr::summarise(total = sum(cases)) %>%
  tidyr::pivot_wider(names_from =  type, 
                     values_from = total) %>%
  dplyr::mutate(unrecovered = confirmed - ifelse(is.na(recovered), 0, recovered) - ifelse(is.na(death), 0, death)) %>%
  dplyr::arrange(-confirmed) %>%
  dplyr::ungroup() %>%
  dplyr::mutate(country = dplyr::if_else(Country.Region == "United Arab Emirates", "UAE", Country.Region)) %>%
  dplyr::mutate(country = dplyr::if_else(country == "Mainland China", "China", country)) %>%
  dplyr::mutate(country = dplyr::if_else(country == "North Macedonia", "N.Macedonia", country)) %>%
  dplyr::mutate(country = trimws(country)) %>%
  dplyr::mutate(country = factor(country, levels = country))

df_daily <- coronavirus %>% 
  dplyr::group_by(date, type) %>%
  dplyr::summarise(total = sum(cases, na.rm = TRUE)) %>%
  tidyr::pivot_wider(names_from = type,
                     values_from = total) %>%
  dplyr::arrange(date) %>%
  dplyr::ungroup() %>%
  dplyr::mutate(active =  confirmed - death - recovered) %>%
  dplyr::mutate(confirmed_cum = cumsum(confirmed),
                death_cum = cumsum(death),
                recovered_cum = cumsum(recovered),
                active_cum = cumsum(active))
  

df1 <- coronavirus %>% dplyr::filter(date == max(date))


#------------trajectory plot data prep------------

df_china <- coronavirus %>% dplyr::filter(type == "confirmed", Country.Region == "China") %>%
  dplyr::group_by(date) %>%
  dplyr::summarise(cases = sum(cases)) %>%
  dplyr::ungroup() %>%
  dplyr::arrange(date) %>%
  dplyr::mutate(china = cumsum(cases)) %>%
  dplyr::filter(china > 100)  %>%
  dplyr::select(-cases, -date)
df_china$index <- 1:nrow(df_china)


df_uk <- coronavirus %>% dplyr::filter(type == "confirmed", Country.Region == "United Kingdom") %>%
  dplyr::group_by(date) %>%
  dplyr::summarise(cases = sum(cases)) %>%
  dplyr::ungroup() %>%
  dplyr::arrange(date) %>%
  dplyr::mutate(uk = cumsum(cases)) %>%
  dplyr::filter(uk > 100)  %>%
  dplyr::select(-cases, -date)
df_uk$index <- 1:nrow(df_uk)


df_fr <- coronavirus %>% dplyr::filter(type == "confirmed", Country.Region == "France") %>%
  dplyr::group_by(date) %>%
  dplyr::summarise(cases = sum(cases)) %>%
  dplyr::ungroup() %>%
  dplyr::arrange(date) %>%
  dplyr::mutate(france = cumsum(cases)) %>%
  dplyr::filter(france > 100)  %>%
  dplyr::select(-cases, -date)
df_fr$index <- 1:nrow(df_fr)

df_us <- coronavirus %>% dplyr::filter(type == "confirmed", Country.Region == "US") %>%
  dplyr::group_by(date) %>%
  dplyr::summarise(cases = sum(cases)) %>%
  dplyr::ungroup() %>%
  dplyr::arrange(date) %>%
  dplyr::mutate(us = cumsum(cases)) %>%
  dplyr::filter(us > 100)  %>%
  dplyr::select(-cases, -date)
df_us$index <- 1:nrow(df_us)

df_iran <- coronavirus %>% dplyr::filter(type == "confirmed", Country.Region == "Iran") %>%
  dplyr::group_by(date) %>%
  dplyr::summarise(cases = sum(cases)) %>%
  dplyr::ungroup() %>%
  dplyr::arrange(date) %>%
  dplyr::mutate(iran = cumsum(cases)) %>%
  dplyr::filter(iran > 100)  %>%
  dplyr::select(-cases, -date)
df_iran$index <- 1:nrow(df_iran)

df_sk <- coronavirus %>% dplyr::filter(type == "confirmed", Country.Region == "Korea, South") %>%
  dplyr::group_by(date) %>%
  dplyr::summarise(cases = sum(cases)) %>%
  dplyr::ungroup() %>%
  dplyr::arrange(date) %>%
  dplyr::mutate(sk = cumsum(cases)) %>%
  dplyr::filter(sk > 100)  %>%
  dplyr::select(-cases, -date)
df_sk$index <- 1:nrow(df_sk)

df_spain <- coronavirus %>% dplyr::filter(type == "confirmed", Country.Region == "Spain") %>%
  dplyr::group_by(date) %>%
  dplyr::summarise(cases = sum(cases)) %>%
  dplyr::ungroup() %>%
  dplyr::arrange(date) %>%
  dplyr::mutate(spain = cumsum(cases)) %>%
  dplyr::filter(spain > 100)  %>%
  dplyr::select(-cases, -date)
df_spain$index <- 1:nrow(df_spain)



df_italy <- italy_total %>% dplyr::select(date, italy = cumulative_cases) %>%
  dplyr::filter(italy > 100) %>%
  dplyr::select(-date)
df_italy$index <- 1:nrow(df_italy)

df_trajectory <- df_china %>% 
  dplyr::left_join(df_italy, by = "index") %>%
  dplyr::left_join(df_iran, by = "index") %>%
  dplyr::left_join(df_sk, by = "index") %>%
  dplyr::left_join(df_us, by = "index") %>%
  dplyr::left_join(df_fr, by = "index") %>%
  dplyr::left_join(df_uk, by = "index") %>%
  dplyr::left_join(df_spain, by = "index")



```


Summary
=======================================================================
Row
-----------------------------------------------------------------------

### confirmed {.value-box}

```{r}

valueBox(value = paste(format(sum(df$confirmed), big.mark = ","), "", sep = " "), 
         caption = "Total Confirmed Cases", 
         icon = "fas fa-user-md", 
         color = confirmed_color)
```


### active {.value-box}

```{r}
valueBox(value = paste(format(sum(df$unrecovered, na.rm = TRUE), big.mark = ","), " (",
                       round(100 * sum(df$unrecovered, na.rm = TRUE) / sum(df$confirmed), 1), 
                       "%)", sep = ""), 
         caption = "Active Cases", icon = "fas fa-ambulance", 
         color = active_color)
```

### recovered {.value-box}

```{r}
valueBox(value = paste(format(sum(df$recovered, na.rm = TRUE), big.mark = ","), " (",
                       round(100 * sum(df$recovered, na.rm = TRUE) / sum(df$confirmed), 1), 
                       "%)", sep = ""), 
         caption = "Recovered Cases", icon = "fas fa-heartbeat", 
         color = recovered_color)
```

### death {.value-box}

```{r}

valueBox(value = paste(format(sum(df$death, na.rm = TRUE), big.mark = ","), " (",
                       round(100 * sum(df$death, na.rm = TRUE) / sum(df$confirmed), 1), 
                       "%)", sep = ""),
         caption = "Death Cases", 
         icon = "fas fa-heart-broken", 
         color = death_color)
```


Row
-----------------------------------------------------------------------

### Cases Distribution by Type (Top 25 Countries) 

```{r daily_summary}


plotly::plot_ly(data = df[1:30,], 
                x = ~ country, 
                y = ~ unrecovered, 
                # text =  ~ confirmed, 
                # textposition = 'auto',
                type = "bar", 
                name = "Active",
                marker = list(color = active_color)) %>%
  plotly::add_trace(y = ~ recovered, 
                    # text =  ~ recovered, 
                    # textposition = 'auto',
                    name = "Recovered",
                    marker = list(color = recovered_color)) %>%
  plotly::add_trace(y = ~ death, 
                    # text =  ~ death, 
                    # textposition = 'auto',
                    name = "Death",
                    marker = list(color = death_color)) %>%
  plotly::layout(title = "",
                 barmode = 'stack',
                 yaxis = list(title = "Total Cases (log scaled)",
                              type = "log"),
                 xaxis = list(title = paste("Last update:", format(max(coronavirus::coronavirus$date), '%d %B'), sep = " ")),
                 hovermode = "compare",
                 annotations = list(
                   text = paste("Last update:", format(max(coronavirus::coronavirus$date), '%d %B'), sep = " "),
                   xref = "paper",
                   yref = "paper",
                   showarrow = FALSE,
                  x = 0.95,
                  y = 1
                 ),
                 margin =  list(
                   # l = 60,
                   # r = 40,
                   b = 10,
                   t = 10,
                   pad = 2
                 ))





```

Row {data-width=400}
-----------------------------------------------------------------------


### Daily Cumulative Cases by Type
    
```{r}

# plotly::plot_ly(df_daily, x = ~date, y = ~active_cum, name = 'Active', type = 'scatter', mode = 'none', stackgroup = 'one', fillcolor = "#1f77b4") %>%
# plotly::add_trace(y = ~recovered_cum, name = 'Recovered', fillcolor = "green") %>%
# plotly::add_trace(y = ~death_cum, name = "Death", fillcolor = "red") %>%
#   plotly::layout(title = "",
#          xaxis = list(title = "",
#                       showgrid = FALSE),
#          yaxis = list(title = "Cumulative Number of Cases",
#                       showgrid = FALSE),
#          legend = list(x = 0.1, y = 0.9),
#                  hovermode = "compare")


plotly::plot_ly(data = df_daily,
                x = ~ date,
                y = ~ active_cum, 
                name = 'Active', 
                fillcolor = active_color,
                type = 'scatter',
                mode = 'none', 
                stackgroup = 'one') %>%
  plotly::add_trace(y = ~ recovered_cum,
                    name = "Recovered",
                    fillcolor = recovered_color) %>%
  plotly::add_trace(y = ~ death_cum,
                    name = "Death",
                    fillcolor = death_color) %>%
  plotly::layout(title = "",
                 yaxis = list(title = "Cumulative Number of Cases"),
                 xaxis = list(title = "Date"),
                 legend = list(x = 0.1, y = 0.9),
                 hovermode = "compare")
  

```


### Recovery and Death Rates by Country
    
```{r}
df_summary <-coronavirus %>% 
  # dplyr::filter(Country.Region != "Others") %>%
  dplyr::group_by(Country.Region, type) %>%
  dplyr::summarise(total_cases = sum(cases)) %>%
  tidyr::pivot_wider(names_from = type, values_from = total_cases) %>%
  dplyr::arrange(- confirmed) %>%
  dplyr::filter(confirmed >= 25) %>%
  dplyr::select(country = Country.Region, confirmed, recovered, death) %>%
  dplyr::mutate(recover_rate = recovered / confirmed,
         death_rate = death / confirmed)  
df_summary %>%
  DT::datatable(rownames = FALSE,
            colnames = c("Country", "Confirmed", "Recovered", "Death", "Recovery Rate", "Death Rate"),
            options = list(pageLength = nrow(df_summary), dom = 'tip')) %>%
  DT::formatPercentage("recover_rate", 2) %>%
  DT::formatPercentage("death_rate", 2) 
```


Map
=======================================================================

**Map**

```{r map}
# map tab added by Art Steinmetz

cv_data_for_plot <- coronavirus %>% 
  dplyr::filter(cases > 0) %>% 
  dplyr::group_by(Country.Region,Province.State,Lat,Long,type) %>% 
  dplyr::summarise(cases = sum(cases)) %>% 
  dplyr::mutate(log_cases = 2 * log(cases)) %>% 
  dplyr::ungroup()
cv_data_for_plot.split <- cv_data_for_plot %>% split(cv_data_for_plot$type)
pal <- colorFactor(c("orange", "red","green"), domain = c("confirmed", "death","recovered"))
map_object <- leaflet() %>% addProviderTiles(providers$Stamen.Toner)
names(cv_data_for_plot.split) %>%
  purrr::walk( function(df) {
    map_object <<- map_object %>%
      addCircleMarkers(data=cv_data_for_plot.split[[df]],
                 lng=~Long, lat=~Lat,
#                 label=~as.character(cases),
                 color = ~pal(type),
                 stroke = FALSE,
                 fillOpacity = 0.8,
                 radius = ~log_cases,
                 # popup =  leafpop::popupTable(cv_data_for_plot.split[[df]],
                 popup =  popupTable(cv_data_for_plot.split[[df]],
                                              feature.id = FALSE,
                                              row.numbers = FALSE,
                                              zcol=c("type","cases","Country.Region","Province.State")),
                 group = df,
#                 clusterOptions = markerClusterOptions(removeOutsideVisibleBounds = F),
                 labelOptions = labelOptions(noHide = F,
                                             direction = 'auto'))
  })
map_object %>%
  addLayersControl(
    overlayGroups = names(cv_data_for_plot.split),
    options = layersControlOptions(collapsed = FALSE) 
  )
```

Trends
=======================================================================


Column {data-width=400}
-------------------------------------
    
### New Cases - Top 15 Countries (`r  max(coronavirus$date)`)
    
```{r new_cases}
max_date <- max(coronavirus$date)
coronavirus %>% 
  dplyr::filter(type == "confirmed", date == max_date) %>%
  dplyr::group_by(Country.Region) %>%
  dplyr::summarise(total_cases = sum(cases)) %>%
  dplyr::arrange(-total_cases) %>%
  dplyr::mutate(country = factor(Country.Region, levels = Country.Region)) %>%
  dplyr::ungroup() %>%
  dplyr::top_n(n = 15, wt = total_cases) %>%
  plotly::plot_ly(x = ~ country,
                  y = ~ total_cases,
                  text = ~ total_cases,
                  textposition = 'auto',
                  type = "bar") %>%
  plotly::layout(yaxis = list(title = "Number of Cases"),
                 xaxis = list(title = ""),
                 margin =  list(
                   l = 10,
                   r = 10,
                   b = 10,
                   t = 10,
                   pad = 2
                 ))

```


### Trajectory Plot - Major Countries 

```{r}
plotly::plot_ly(data = df_trajectory) %>%
  plotly::add_lines(x = ~ index,
                    y = ~ china,
                    name = "China",  line = list(width = 2)) %>%
  plotly::add_lines(x = ~ index,
                    y = ~ italy,
                    line = list(color = "red", width = 2),
                    name = "Italy") %>%
  plotly::add_lines(x = ~ index,
                    y = ~ us,
                    name = "United States",  line = list(width = 2)) %>%
    plotly::add_lines(x = ~ index,
                    y = ~ uk,
                    name = "United Kingdom",  line = list(width = 2)) %>%
      plotly::add_lines(x = ~ index,
                    y = ~ france,
                    name = "France",  line = list(width = 2)) %>%
  plotly::add_lines(x = ~ index,
                    y = ~ iran,
                    name = "Iran",  line = list(color = "orange", width = 2)) %>%
  plotly::add_lines(x = ~ index,
                    y = ~ sk,
                    name = "South Korea",  line = list(width = 2)) %>%
  plotly::add_lines(x = ~ index,
                    y = ~ spain,
                    name = "Spain") %>%
  plotly::layout(yaxis = list(title = "Cumulative Positive Cases",type = "log"),
                 xaxis = list(title = "Days since the total positive cases surpass 100"),
                 legend = list(x = 0.7, y = 0.3),
                 hovermode = "compare")
```
   
Column {data-width=600}
-------------------------------------
   
### Recovery and Death Rates for Countries with at Least 10000 Cases

```{r}
coronavirus::coronavirus %>% 
  # dplyr::filter(Country.Region != "Others") %>%
  dplyr::group_by(Country.Region, type) %>%
  dplyr::summarise(total_cases = sum(cases)) %>%
  tidyr::pivot_wider(names_from = type, values_from = total_cases) %>%
  dplyr::arrange(- confirmed) %>%
  dplyr::filter(confirmed >= 10000) %>%
  dplyr::mutate(recover_rate = recovered / confirmed,
                death_rate = death / confirmed) %>% 
  dplyr::mutate(recover_rate = dplyr::if_else(is.na(recover_rate), 0, recover_rate),
                death_rate = dplyr::if_else(is.na(death_rate), 0, death_rate)) %>%
  dplyr::ungroup() %>%
  dplyr::mutate(confirmed_normal = as.numeric(confirmed) / max(as.numeric(confirmed))) %>%
  plotly::plot_ly(y = ~ round(100 * recover_rate, 1),
                  x = ~ round(100 * death_rate, 1),
                  size = ~  log(confirmed),
                  sizes = c(5, 70),
                  type = 'scatter', mode = 'markers',
                  color = ~ Country.Region,
                  marker = list(sizemode = 'diameter' , opacity = 0.5),
                  hoverinfo = 'text',
                  text = ~paste("
", Country.Region, 
                                "
 Confirmed Cases: ", confirmed,
                                "
 Recovery Rate: ", paste(round(100 * recover_rate, 1), "%", sep = ""),
                                "
 Death Rate: ",  paste(round(100 * death_rate, 1), "%", sep = ""))
                 ) %>%
  plotly::layout(yaxis = list(title = "Recovery Rate", ticksuffix = "%"),
                xaxis = list(title = "Death Rate", ticksuffix = "%", 
                             dtick = 1, 
                             tick0 = 0),
                hovermode = "compare")
  
```   
 
### Cases Status Update for `r  max(coronavirus$date)`
    
```{r}
daily_summary <- coronavirus %>% 
  dplyr::filter(date == max(date)) %>%
  dplyr::group_by(Country.Region, type) %>%
  dplyr::summarise(total = sum(cases)) %>%
  tidyr::pivot_wider(names_from = type, values_from = total) %>%
  dplyr::arrange(-confirmed) %>%
  dplyr::select(country = Country.Region, confirmed, recovered, death)
  
  
  DT::datatable(data = daily_summary,
                rownames = FALSE,
                colnames = c("Country", "Confirmed", "Recovered", "Death"),
                options = list(pageLength = nrow(daily_summary), dom = 'tip'))
```

Data
=======================================================================

```{r}
coronavirus %>% 
  dplyr::select(Date = date, Province = Province.State, Country = Country.Region, `Case Type` = type, `Number of Cases` = cases) %>%
  DT::datatable(rownames = FALSE,
            options = list(searchHighlight = TRUE, 
                           pageLength = 20), filter = 'top')
```



About
=======================================================================

**The Coronavirus Dashboard**

Last updated: `r format(max(coronavirus::coronavirus$date), '%d %B')`

This Coronavirus dashboard provides an overview of the 2019 Novel Coronavirus COVID-19 (2019-nCoV) epidemic. This dashboard is built with R using the Rmakrdown framework and can easily reproduce by others. The code behind the dashboard available [here](https://github.com/RamiKrispin/coronavirus_dashboard)

**Data**

The input data for this dashboard is the [coronavirus](https://github.com/RamiKrispin/coronavirus) R package (dev version). The data and dashboard is refreshed on a daily bases. The raw data pulled from the Johns Hopkins University Center for Systems Science and Engineering (JHU CCSE) Coronavirus [repository](https://github.com/RamiKrispin/coronavirus-csv)




**Packages**

* Dashboard interface - the [flexdashboard](https://rmarkdown.rstudio.com/flexdashboard/) package. 
* Visualization - the [plotly](https://plot.ly/r/) package for the plots and [leaflet](https://rstudio.github.io/leaflet/) for the map
* Data manipulation - [dplyr](https://dplyr.tidyverse.org/), and [tidyr](https://tidyr.tidyverse.org/)
* Tables - the [DT](https://rstudio.github.io/DT/) package

**Deployment and reproducibly**

The dashboard was deployed to Github docs. If you wish to deploy and/or modify the dashboard on your Github account, you can apply the following steps:

* Fork the dashboard [repository](https://github.com/RamiKrispin/coronavirus_dashboard), or
* Clone it and push it to your Github package
* Here some general guidance about deployment of flexdashboard on Github page - [link](https://github.com/pbatey/flexdashboard-example)

For any question or feedback, you can either open an [issue](https://github.com/RamiKrispin/coronavirus_dashboard/issues) or contact me on [Twitter](https://twitter.com/Rami_Krispin).

**Contribution** 

The **Map** tab was contributed by [Art Steinmetz](@adababbage) on this [pull request](https://github.com/RamiKrispin/coronavirus_dashboard/pull/1). Thanks Art!